Backend Engineer

Senior Backend Engineer – AI/LLM

About the Role

We are seeking a Senior Backend Engineer to join our innovation team. In this pivotal role, you will help build the AI-native backbone of our platform by designing production-grade backend systems where Artificial Intelligence is a first-class component. Key focus areas include multi-agent orchestration, Retrieval-Augmented Generation (RAG), and provider-agnostic Large Language Model (LLM) integrations.

Key Responsibilities

• Design and scale asynchronous REST/WebSocket APIs in Python using FastAPI or similar frameworks.
• Apply dependency injection, type hints, and clean vertical-slice/service architecture principles.
• Implement multi-agent workflows, including sequential, concurrent, and handoff patterns.
• Integrate multiple LLM providers through a provider-agnostic layer to support A/B testing and cost-aware routing.
• Build and maintain RAG pipelines using vector stores such as pgvector, Chroma, or managed vector search services.
• Design and evolve relational database schemas and data models using SQLAlchemy/SQLModel-style ORM and migrations.
• Instrument services with structured logging, distributed tracing, and cost/latency metrics to ensure optimal performance (including p95 response-time targets).
• Maintain production standards by owning end-to-end CI/CD processes, including linting, type checking, testing, packaging, and deployment.

Required Qualifications

• 5+ years of experience building production backend systems in Python with real-world asynchronous I/O expertise.
• Hands-on experience designing and scaling REST or asynchronous APIs (FastAPI).
• Practical experience integrating LLM APIs such as OpenAI, Gemini, or similar models.
• Strong skills in vector databases, RAG-style retrieval architectures, relational database design, schema optimization, and migrations.
• Demonstrated ability to use AI across the software delivery lifecycle beyond simple code generation (e.g., evaluating model appropriateness for specific problems).
• Experience reviewing AI-generated code, understanding its failure modes, and establishing AI delivery guardrails regarding provenance, licensing, and customer data security.